Design by neural network of concentric multilayered cylindrical metamaterials. (18th March 2020)

• Record Type: Journal Article
• Authors: Akashi, Naoto; Toma, Mana; Kajikawa, Kotaro
• Is Part Of: Applied physics express. Volume 13:Number 4(2020)
• Publication Date: 2020-03-18
• Subjects: neural network -- inverse design -- metamaterials; Physics -- Periodicals; Technology -- Periodicals; 621.05
• DOI: 10.35848/1882-0786/ab7cf1
• Languages: English
• ISSNs: 1882-0778

Abstract

Abstract: Artificial neural networks (NNs) that have deeply learned the optical responses from metamaterials can predict the optical spectra from a given metamaterial without solving Maxwell's equations. Prediction is extremely fast because of the low computational complexity. We report here two inverse designs of concentric multilayered cylinder metamaterials, using trained NN models, and discuss the accuracy of the prediction. We also predict a cloaking condition for invisibility having performance better than that derived by transformation optics, as a further application of NNs to metamaterial design.